End of training

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4075
+- Loss: 1.4202
 
 ## Model description
 

logs/events.out.tfevents.1706094350.f329f175c73d.27.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b978678a5bfa88c552c340ea38321eccb93f5026e6584ccb7c317d95a4efa8b
-size 1719110
+oid sha256:36ff5be3735804ba76dacc3f4c5c76cabe43a1e10213238b24dd25242261b020
+size 1719546

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136ec0a13ad6ab3edb0074ad3fb89f92f9207f0b0b9a7103444757ea429abe34
+oid sha256:78408bc361c088697d6742a9a787eecd40f5b3bf9f7dfe66d0f775ee2a9c3230
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 30.321657123610642,
+  "epoch": 31.332098349612664,
   "eval_steps": 750,
-  "global_step": 22500,
+  "global_step": 23250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -436,6 +436,20 @@
       "eval_samples_per_second": 59.292,
       "eval_steps_per_second": 0.937,
       "step": 22500
+    },
+    {
+      "epoch": 31.33,
+      "learning_rate": 4.3939353099730465e-05,
+      "loss": 0.5533,
+      "step": 23250
+    },
+    {
+      "epoch": 31.33,
+      "eval_loss": 1.4201693534851074,
+      "eval_runtime": 84.3754,
+      "eval_samples_per_second": 59.259,
+      "eval_steps_per_second": 0.936,
+      "step": 23250
     }
   ],
   "logging_steps": 750,
@@ -443,7 +457,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 9.737983724658278e+17,
+  "total_flos": 1.0062582280409088e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null